© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 91157
    Prev
    Next
    INDEX
    Explanations

    pathogenesis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     holographic
    -0.77
     Carefully
    -0.50
    etna
    -0.43
     kadang
    -0.41
    znam
    -0.41
    u
    -0.41
    ovatel
    -0.41
    he
    -0.40
    ary
    -0.40
     folgt
    -0.40
    POSITIVE LOGITS
    Personendaten
    0.84
     AssemblyCulture
    0.82
     ProtoMessage
    0.77
     مرئيه
    0.76
    DataAnnotations
    0.74
     تانيه
    0.69
    awtextra
    0.69
    IonicModule
    0.69
    AddTagHelper
    0.68
    featureID
    0.67
    Activations Density 0.063%

    No Known Activations